About the job
Join Edra as an AI Engineer
At Edra, we are tackling one of the most challenging issues in enterprise AI: the mismatch between generic AI models and specific company processes. We are developing AI agents that learn to navigate and execute processes as they truly operate.
As a Series A startup, supported by Sequoia and other notable venture capital firms, we are expanding our teams in New York and London. Our workforce is composed of exceptionally skilled engineers, AI researchers, and strategists who believe that outstanding talent is the cornerstone of our success.
Your Role
You will be instrumental in creating a learning system that equips AI agents with the knowledge of how enterprises function. This system will assimilate knowledge bases, dialogues, tickets, and system logs, generating written directives that agents can confidently execute, including a scoring mechanism to determine when to automate tasks or request human intervention.
We seek AI Engineers with a track record of building intricate, production-ready LLM-based systems. If you've scaled LLM workflows to manage millions of requests, developed multi-agent systems in live environments, or created evaluation frameworks for enterprise applications, we want you. Your contributions will directly impact our core learning library, and you will ship features that serve actual enterprise customers while enhancing the platform. This role covers continuous learning systems, agentic features, human-in-the-loop feedback mechanisms, and orchestration of AI agents.
Your Responsibilities
Contribute to our core context learning library by implementing new learning capabilities and generalizing them for broader platform use.
Design and execute LLM-powered systems and workflows from initial concept to production.
Collaborate with enterprise customers to identify issues, prototype solutions, and bring them to production.
Develop agentic features for knowledge management, enabling agents to autonomously edit, update, and maintain extensive knowledge bases.
Establish reliability and confidence systems, including evaluation frameworks and logic for determining when to automate versus when to escalate to human oversight.
Architect asynchronous, scalable systems for complex AI orchestration.
Influence the direction of our AI strategy and product capabilities.
